网络并行计算是当今并行计算研究的热点。
Network parallel computing is a hot topic in research area at present.
本文简要介绍了如何建立一个简单、易行的微机网络并行计算的开发环境。
This paper introduces how to build up a simple and easy micro computer networked computing system.
从改善用户并行程序设计环境出发，给出了在网络并行计算的一种新平台。
In view of improving the parallel programming environment, the new framework of networks parallel computing is put forward.
介绍了曙光- 1 0 0 0A分布式大规模并行计算机系统，讨论了分布式环境下实现网络并行计算的若干技术。
The Dawning 1000A Massively parallel and distributed processors system is introduced in this paper, some techniques about network based parallel computing under distributed are discussed.
该算法能有效地消除不一致信息的干扰，降低神经网络的规模，并且可以实现不同数据类型的属性集之间属性匹配过程的并行计算。
This algorithm can resolve the interference among attributes with different data types, and decrease the size of BP neural network, and realize the parallel computation of attributes matching.
人工神经网络在许多应用领域中建立了一种新的高度并行计算的结构。
In practice neural networks create a new kind of architectures of highly parallel computations.
随着网络技术的飞速发展，分布式并行计算成为可能。
As the rapid development of network technology, it's possible to realize parallel and distributed computing.
它不仅是一个友好的人机界面和具有编辑、格式转化、数据加载等多种功能，而且支持并行计算，如多层BP神经网络及FFT算法。
It is friendly interface with the functions of editing, format transformation, data load, and so on. The software also supports parallel computing of BP algorithm in neural networks and FFT.
计算机网络的主要目的是资源共享、并行计算、冗余。
The main objectives of computer networks are resource sharing, parallel computation and redundancy.
面向神经计算的并行计算机体系结构是神经网络研究中的一项重要工作。
The architecture of neural network computing oriented parallel computer is the elementary aspect of artificial neural network research.
一种并行计算，将计算的元素模仿构成动物神经系统的神经元网络。
Type of parallel computation in which computing elements are modeled on the network of neurons that constitute animal nervous systems.
星形互连网络是一种易于实现大规模并行计算的互连网络拓扑结构。
The star interconnection network is generally considered as an attractive network architecture for parallel computing.
本文给出了分布式环境并行计算程序开发平台的一种新构架，研制了一个网络环境的可视化并行程序设计平台。
The new framework of network parallel computing is put forward in this paper, and a visual parallel programming platform based on network is implemented.
直径是度量并行计算系统网络的容错性和信息延迟的重要参数。
The wide diameter is an important measure for fault tolerance and transmission delay of a parallel processing computer network.
因此研究互连网络及相关的聚合通信算法对提高并行计算机的性能，进而提高并行应用程序的执行效率具有重要的意义。
Thus, the research on interconnection networks and collective communication is crucial to increase the performance of multicomputers so as to improve the execution efficiency of parallel applications.
李东，男，1967年生，教授，主要研究领域为网络信息安全技术，并行计算，计算机系统结构，计算机图形学等。
LI Dong, born in 1967, professor. His research interests include computer network security, parallel computing, computer architecture, and computer graphics.
互连网络结构的设计是实现高性能并行计算机的重要问题之一。
The design of the interconnection architecture is one of the most important tasks for a high performance parallel computer.
主要研究方向：计算机网络与信息安全理论与技术、并行计算等。
Research Fields: the Theory and Technique of Computer network and Information Security; Parallel Computing etc.
此技术可应用于并行计算机互连网络和分布式高性能计算机群的互连网络。
This technology is able to be applied to the parallel computer interconnection network and the network of…
该算法将网络节点按层次进行分类，并分层并行计算各层次的功率损耗和节点电压，因而可大幅度提高配电网潮流的计算速度。
In this algorithm, the nodes of network are sorted by layers and the loss of voltage and power of speed of power flow can be increased greatly.
网络连接机群是一种有效的并行计算工具，讨论了在此环境下流场分析和设计的并行计算问题。
A network of computers connected via Ethernet is one of effective parallel computation tools. Parallel computation of flow field analysis and design on this kind of network are carried out.
此技术可应用于并行计算机互连网络和分布式高性能计算机群的互连网络。
This technology is able to be applied to the parallel computer interconnection network and the network of the distributed high performance co…
用网络并行思路探讨了结构损伤动力有限元并行分析算法的实现方法，并在曙光- 1 0 0 0A分布式并行计算机上进行了测试。
The parallel algorithm for dynamic finite element analysis of damaged structure is discussed in this paper, and the test is done on Dawning 1000a massively parallel processors system.
用网络并行思路探讨了结构损伤动力有限元并行分析算法的实现方法，并在曙光- 1 0 0 0A分布式并行计算机上进行了测试。
The parallel algorithm for dynamic finite element analysis of damaged structure is discussed in this paper, and the test is done on Dawning 1000a massively parallel processors system.
应用推荐